© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62293
    Prev
    Next
    INDEX
    Explanations

    principle or principles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    身临åħ¶å¢ĥ
    -0.10
    گاÙĩÛĮ
    -0.09
    ness
    -0.09
    åħ¨å¿ĥåħ¨æĦı
    -0.09
    regon
    -0.09
    ä¸įèĥľæĶ¶
    -0.09
    çĺ¢
    -0.09
    lands
    -0.08
    åħ¢åħ¢ä¸ļä¸ļ
    -0.08
    gether
    -0.08
    POSITIVE LOGITS
    fully
    0.09
    æĢ§åľ°
    0.08
    ately
    0.08
    chen
    0.08
     tắc
    0.08
    aus
    0.07
    acle
    0.07
    ful
    0.07
    aire
    0.07
    alement
    0.07
    Activations Density 0.024%

    No Known Activations